diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
index 03c4ef3e4939d9f03b765508a086284e4791a802..4335f3b9ff701a2ad88b2d97e9c906cf13bf5fcc 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,24 @@
---
+language:
+- en
license: llama3
+tags:
+- Llama-3
+- instruct
+- finetune
+- chatml
+- gpt4
+- synthetic data
+- distillation
+- function calling
+- json mode
+- axolotl
+- roleplaying
+- chat
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+base_model_relation: quantized
+library_name: mlc-llm
+pipeline_tag: text-generation
---
+
+3-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B) for inference with the [Private LLM](http://privatellm.app) app.
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2f98e357c05745bf2cf79816dbac3b1d79de5789
--- /dev/null
+++ b/config.json
@@ -0,0 +1,5 @@
+{
+ "quantization_config": {
+ "bits": 3
+ }
+}
diff --git a/ndarray-cache.json b/ndarray-cache.json
new file mode 100644
index 0000000000000000000000000000000000000000..01374ae0465f31f382948580721e4fb5ad36bfe5
--- /dev/null
+++ b/ndarray-cache.json
@@ -0,0 +1,4311 @@
+{
+ "metadata": {
+ "ParamSize": 325,
+ "ParamBytes": 3631664128.0,
+ "BitsPerParam": 2.6739310072364444
+ },
+ "records": [
+ {
+ "dataPath": "params_shard_0.bin",
+ "format": "raw-shard",
+ "nbytes": 211365888,
+ "records": [
+ {
+ "name": "lm_head.q_weight",
+ "shape": [
+ 128256,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 211365888,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "48c08152fc14b2a618e78437162e4262"
+ },
+ {
+ "dataPath": "params_shard_1.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.30.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "b7bd9b67ab59e38c00fba18ea2f3ba84"
+ },
+ {
+ "dataPath": "params_shard_2.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.30.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "28c0b02fa1a69aff387f35ab19e926ce"
+ },
+ {
+ "dataPath": "params_shard_3.bin",
+ "format": "raw-shard",
+ "nbytes": 29369856,
+ "records": [
+ {
+ "name": "lm_head.q_scale",
+ "shape": [
+ 128256,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 26420736,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.30.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 26420736
+ },
+ {
+ "name": "model.layers.30.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 26428928
+ }
+ ],
+ "md5sum": "6c9827ff5c02bf722e115fe7e4069933"
+ },
+ {
+ "dataPath": "params_shard_4.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.31.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "7d3228d96f64aa54af6787d3bcd01834"
+ },
+ {
+ "dataPath": "params_shard_5.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.31.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "0be95009a2234474dd771519915dee70"
+ },
+ {
+ "dataPath": "params_shard_6.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.30.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.30.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.30.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.30.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 12664832
+ },
+ {
+ "name": "model.layers.30.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 13508608
+ },
+ {
+ "name": "model.layers.30.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 23633920
+ },
+ {
+ "name": "model.layers.31.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.31.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "08a07d3318553147f295efe7271e3ef8"
+ },
+ {
+ "dataPath": "params_shard_7.bin",
+ "format": "raw-shard",
+ "nbytes": 211365888,
+ "records": [
+ {
+ "name": "model.embed_tokens.q_weight",
+ "shape": [
+ 128256,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 211365888,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "fc41b3530388be6f5b5f670666b46076"
+ },
+ {
+ "dataPath": "params_shard_8.bin",
+ "format": "raw-shard",
+ "nbytes": 26420736,
+ "records": [
+ {
+ "name": "model.embed_tokens.q_scale",
+ "shape": [
+ 128256,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 26420736,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "7275a19f5d55f404043e9e4e380007e0"
+ },
+ {
+ "dataPath": "params_shard_9.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.0.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "dee42fa2b52538657933945571b1bdfb"
+ },
+ {
+ "dataPath": "params_shard_10.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.0.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "1b75bd9db390a195350925cf3b34838c"
+ },
+ {
+ "dataPath": "params_shard_11.bin",
+ "format": "raw-shard",
+ "nbytes": 27856896,
+ "records": [
+ {
+ "name": "model.layers.31.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.31.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.31.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.31.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.31.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.31.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.norm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.0.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24907776
+ },
+ {
+ "name": "model.layers.0.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24915968
+ }
+ ],
+ "md5sum": "b5d028c259ffdd1f953e4b08d2480160"
+ },
+ {
+ "dataPath": "params_shard_12.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.1.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "52f5705f444735ecd47c944d732092ee"
+ },
+ {
+ "dataPath": "params_shard_13.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.1.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "fa50e96e2cbf8158ff1f5fd9282c089c"
+ },
+ {
+ "dataPath": "params_shard_14.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.0.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.0.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.0.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.0.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.0.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.0.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.1.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.1.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "f4ba04f1756a7120aeff3877a3ffef42"
+ },
+ {
+ "dataPath": "params_shard_15.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.2.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f33d719b68d257d66eb7d1f3673d778b"
+ },
+ {
+ "dataPath": "params_shard_16.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.2.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a496da0c6f5fc26850b9bb5666571d20"
+ },
+ {
+ "dataPath": "params_shard_17.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.1.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.1.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.1.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.1.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.1.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.1.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.2.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.2.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "29dff366bda388c0158bd45de6e46069"
+ },
+ {
+ "dataPath": "params_shard_18.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.3.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "c36d92e1674cea560c727a3151ed7c41"
+ },
+ {
+ "dataPath": "params_shard_19.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.3.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "9e41f534d1d9d9963424c96d04ad42e7"
+ },
+ {
+ "dataPath": "params_shard_20.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.2.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.2.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.2.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.2.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.2.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.2.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.3.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.3.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "12268871ad14631d5742a20823f74ff9"
+ },
+ {
+ "dataPath": "params_shard_21.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.4.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "4a1a6a45fc08582b48ccbc3b10f436df"
+ },
+ {
+ "dataPath": "params_shard_22.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.4.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "1b3794bd75f14e183a259f03e48eba17"
+ },
+ {
+ "dataPath": "params_shard_23.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.3.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.3.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.3.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.3.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.3.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.3.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.4.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.4.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "b713d79fcc147131121c8d8f7a4d7b1c"
+ },
+ {
+ "dataPath": "params_shard_24.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.5.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "c3e99d3b9ea603dc15c2444543aa59c0"
+ },
+ {
+ "dataPath": "params_shard_25.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.5.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "72ebe02270dac26ddb7a45a78b938da4"
+ },
+ {
+ "dataPath": "params_shard_26.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.4.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.4.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.4.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.4.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.4.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.4.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.5.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.5.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "5808a28d4022aed03b66281b0cbb6c05"
+ },
+ {
+ "dataPath": "params_shard_27.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.6.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a151a2f2a6e4d4699fa1e721374f32c5"
+ },
+ {
+ "dataPath": "params_shard_28.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.6.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "21a048ca4b94cf5b12ffec3b7b64b1b4"
+ },
+ {
+ "dataPath": "params_shard_29.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.5.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.5.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.5.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.5.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.5.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.5.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.6.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.6.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "8c286af07f8e0aa287bf0238985a7de5"
+ },
+ {
+ "dataPath": "params_shard_30.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.7.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "5bf42152b65361d5d93f1e56f9db313a"
+ },
+ {
+ "dataPath": "params_shard_31.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.7.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "fe4e889b4c33913399aea01c3b3003a8"
+ },
+ {
+ "dataPath": "params_shard_32.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.6.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.6.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.6.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.6.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.6.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.6.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.7.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.7.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "da6a5540333fdfbf1a471cce775e69ba"
+ },
+ {
+ "dataPath": "params_shard_33.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.8.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f856a2b0f782f989c62cfaedfd1997b9"
+ },
+ {
+ "dataPath": "params_shard_34.bin",
+ "format": "raw-shard",
+ "nbytes": 30806016,
+ "records": [
+ {
+ "name": "model.layers.7.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.7.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.7.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.7.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.7.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.7.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.8.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 24899584
+ }
+ ],
+ "md5sum": "48c64694bf7132f81f9216107a34f0b2"
+ },
+ {
+ "dataPath": "params_shard_35.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.10.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "50725ac9c30ae01186106238c9c9d7d3"
+ },
+ {
+ "dataPath": "params_shard_36.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.10.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "de5fc371ae42ebe9be500a497c669e93"
+ },
+ {
+ "dataPath": "params_shard_37.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.8.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.8.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 10125312
+ },
+ {
+ "name": "model.layers.8.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 11390976
+ },
+ {
+ "name": "model.layers.8.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 18141184
+ },
+ {
+ "name": "model.layers.10.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 18984960
+ },
+ {
+ "name": "model.layers.10.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 18993152
+ },
+ {
+ "name": "model.layers.10.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 21934080
+ },
+ {
+ "name": "model.layers.10.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 27840512
+ }
+ ],
+ "md5sum": "d209c888cbf92d03e926ca0641513c55"
+ },
+ {
+ "dataPath": "params_shard_38.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.11.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e2455e669ca1260d668bfac1830bfe50"
+ },
+ {
+ "dataPath": "params_shard_39.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.11.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "4a1e7cbcb6d2af3f014462387528d1ba"
+ },
+ {
+ "dataPath": "params_shard_40.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.10.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.10.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 10125312
+ },
+ {
+ "name": "model.layers.10.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 11390976
+ },
+ {
+ "name": "model.layers.10.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 18141184
+ },
+ {
+ "name": "model.layers.11.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 18984960
+ },
+ {
+ "name": "model.layers.11.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 18993152
+ },
+ {
+ "name": "model.layers.11.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 21934080
+ },
+ {
+ "name": "model.layers.11.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 27840512
+ }
+ ],
+ "md5sum": "893ac3c6a252e74f3e729e056dc5c4f3"
+ },
+ {
+ "dataPath": "params_shard_41.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.12.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "039f4547b7dca5e638fd2fbf0f6bfebc"
+ },
+ {
+ "dataPath": "params_shard_42.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.12.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e0a7b2f20b5fb20cc79719c94e18f19b"
+ },
+ {
+ "dataPath": "params_shard_43.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.11.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.11.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 10125312
+ },
+ {
+ "name": "model.layers.11.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 11390976
+ },
+ {
+ "name": "model.layers.11.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 18141184
+ },
+ {
+ "name": "model.layers.12.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 18984960
+ },
+ {
+ "name": "model.layers.12.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 18993152
+ },
+ {
+ "name": "model.layers.12.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 21934080
+ },
+ {
+ "name": "model.layers.12.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 27840512
+ }
+ ],
+ "md5sum": "bf4763bf74dcb654da55be46a5fb951a"
+ },
+ {
+ "dataPath": "params_shard_44.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.13.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "558b2d10897355831d728de7e691b689"
+ },
+ {
+ "dataPath": "params_shard_45.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.13.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "1065a4e2f17271df7fb27d9ae794f1c5"
+ },
+ {
+ "dataPath": "params_shard_46.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.12.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.12.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 10125312
+ },
+ {
+ "name": "model.layers.12.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 11390976
+ },
+ {
+ "name": "model.layers.12.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 18141184
+ },
+ {
+ "name": "model.layers.13.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 18984960
+ },
+ {
+ "name": "model.layers.13.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 18993152
+ },
+ {
+ "name": "model.layers.13.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 21934080
+ },
+ {
+ "name": "model.layers.13.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 27840512
+ }
+ ],
+ "md5sum": "13195f49786e7f97ae10c38e3c77e380"
+ },
+ {
+ "dataPath": "params_shard_47.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.14.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "42f35e0d801e962fb672c7d9f632f3c4"
+ },
+ {
+ "dataPath": "params_shard_48.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.14.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "cb132819c8fde910bc16ce0cf76d2f7f"
+ },
+ {
+ "dataPath": "params_shard_49.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.13.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.13.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 10125312
+ },
+ {
+ "name": "model.layers.13.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 11390976
+ },
+ {
+ "name": "model.layers.13.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 18141184
+ },
+ {
+ "name": "model.layers.14.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 18984960
+ },
+ {
+ "name": "model.layers.14.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 18993152
+ },
+ {
+ "name": "model.layers.14.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 21934080
+ },
+ {
+ "name": "model.layers.14.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 27840512
+ }
+ ],
+ "md5sum": "113d486f310d4589ab1d85bf734c9973"
+ },
+ {
+ "dataPath": "params_shard_50.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.15.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "6a04bb380a2f509ddfac54638160a754"
+ },
+ {
+ "dataPath": "params_shard_51.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.15.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "9746c2326c61895202b66e9625b6bc4c"
+ },
+ {
+ "dataPath": "params_shard_52.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.14.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.14.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 10125312
+ },
+ {
+ "name": "model.layers.14.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 11390976
+ },
+ {
+ "name": "model.layers.14.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 18141184
+ },
+ {
+ "name": "model.layers.15.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 18984960
+ },
+ {
+ "name": "model.layers.15.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 18993152
+ },
+ {
+ "name": "model.layers.15.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 21934080
+ },
+ {
+ "name": "model.layers.15.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 27840512
+ }
+ ],
+ "md5sum": "4e50d47c68961d200b4838be9325ec91"
+ },
+ {
+ "dataPath": "params_shard_53.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.16.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "45d458b17b6c2001b06ccf401e5f8385"
+ },
+ {
+ "dataPath": "params_shard_54.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.16.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "1b08199798ec2bb5ef47672648ef4165"
+ },
+ {
+ "dataPath": "params_shard_55.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.15.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.15.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 10125312
+ },
+ {
+ "name": "model.layers.15.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 11390976
+ },
+ {
+ "name": "model.layers.15.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 18141184
+ },
+ {
+ "name": "model.layers.16.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 18984960
+ },
+ {
+ "name": "model.layers.16.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 18993152
+ },
+ {
+ "name": "model.layers.16.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 21934080
+ },
+ {
+ "name": "model.layers.16.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 27840512
+ }
+ ],
+ "md5sum": "a65549689d8d73d620e7177b617fcf87"
+ },
+ {
+ "dataPath": "params_shard_56.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.17.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f4f0ef55b99f5a8075854c66b5b2aa75"
+ },
+ {
+ "dataPath": "params_shard_57.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.17.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "3f1548b107e2971199ff104e8ffcfd25"
+ },
+ {
+ "dataPath": "params_shard_58.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.16.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.16.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 10125312
+ },
+ {
+ "name": "model.layers.16.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 11390976
+ },
+ {
+ "name": "model.layers.16.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 18141184
+ },
+ {
+ "name": "model.layers.17.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 18984960
+ },
+ {
+ "name": "model.layers.17.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 18993152
+ },
+ {
+ "name": "model.layers.17.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 21934080
+ },
+ {
+ "name": "model.layers.17.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 27840512
+ }
+ ],
+ "md5sum": "473c3d2507f67858d231c93c24806e4b"
+ },
+ {
+ "dataPath": "params_shard_59.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.18.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e39873a8775fad6fbd015f8210b99cef"
+ },
+ {
+ "dataPath": "params_shard_60.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.18.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "0175f965590883f64dc2935b129cd673"
+ },
+ {
+ "dataPath": "params_shard_61.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.17.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.17.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 10125312
+ },
+ {
+ "name": "model.layers.17.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 11390976
+ },
+ {
+ "name": "model.layers.17.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 18141184
+ },
+ {
+ "name": "model.layers.18.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 18984960
+ },
+ {
+ "name": "model.layers.18.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 18993152
+ },
+ {
+ "name": "model.layers.18.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 21934080
+ },
+ {
+ "name": "model.layers.18.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 27840512
+ }
+ ],
+ "md5sum": "602aadef4f270446859594800411f67c"
+ },
+ {
+ "dataPath": "params_shard_62.bin",
+ "format": "raw-shard",
+ "nbytes": 30375936,
+ "records": [
+ {
+ "name": "model.layers.18.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.18.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 10125312
+ },
+ {
+ "name": "model.layers.18.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 11390976
+ },
+ {
+ "name": "model.layers.18.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 18141184
+ },
+ {
+ "name": "model.layers.19.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 18984960
+ },
+ {
+ "name": "model.layers.19.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 29110272
+ }
+ ],
+ "md5sum": "faa5bf5482cfd87cbc5fd8a0ed08b9d8"
+ },
+ {
+ "dataPath": "params_shard_63.bin",
+ "format": "raw-shard",
+ "nbytes": 31129600,
+ "records": [
+ {
+ "name": "model.layers.19.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.19.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 6750208
+ },
+ {
+ "name": "model.layers.8.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 7593984
+ },
+ {
+ "name": "model.layers.8.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 7602176
+ }
+ ],
+ "md5sum": "9e9dcf19b65d12c8b7d396a9b5c1d2e8"
+ },
+ {
+ "dataPath": "params_shard_64.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.9.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "41a221733cd9163cbc4bc2a4d1669252"
+ },
+ {
+ "dataPath": "params_shard_65.bin",
+ "format": "raw-shard",
+ "nbytes": 29425664,
+ "records": [
+ {
+ "name": "model.layers.8.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.8.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 2940928
+ },
+ {
+ "name": "model.layers.9.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 2949120
+ },
+ {
+ "name": "model.layers.9.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 2957312
+ },
+ {
+ "name": "model.layers.9.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 26484736
+ }
+ ],
+ "md5sum": "80552fc04650aa533b025295968a27e8"
+ },
+ {
+ "dataPath": "params_shard_66.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.19.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "9c58dee3bef2b89a143a1dfd66e5d763"
+ },
+ {
+ "dataPath": "params_shard_67.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.19.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "115c3a1543da92494c79d0d2f9423a42"
+ },
+ {
+ "dataPath": "params_shard_68.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.9.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.9.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.9.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.9.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.9.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.9.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.19.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.19.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "feb74b1dfb0c6aa81e3197ceb1fe0d79"
+ },
+ {
+ "dataPath": "params_shard_69.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.20.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "ff2e6061fc577af9153e247b8e64f6f9"
+ },
+ {
+ "dataPath": "params_shard_70.bin",
+ "format": "raw-shard",
+ "nbytes": 32391168,
+ "records": [
+ {
+ "name": "model.layers.19.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.19.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.20.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.20.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 5922816
+ },
+ {
+ "name": "model.layers.20.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 29450240
+ }
+ ],
+ "md5sum": "0763778bd4527dd49d909a27e0363b46"
+ },
+ {
+ "dataPath": "params_shard_71.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.21.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "ffac8a861d98b264d63bb6720b886e72"
+ },
+ {
+ "dataPath": "params_shard_72.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.21.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e2494c74f2db2c2eaf20c359e8ef6fb8"
+ },
+ {
+ "dataPath": "params_shard_73.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.20.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.20.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.20.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.20.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.20.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.20.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.21.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.21.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "da422d03a9be8564bcd4159a84f46077"
+ },
+ {
+ "dataPath": "params_shard_74.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.22.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "afc1a70e86293c221777250bbc4a1ce9"
+ },
+ {
+ "dataPath": "params_shard_75.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.22.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "be365d0b81c2ee695369ba100ea56db2"
+ },
+ {
+ "dataPath": "params_shard_76.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.21.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.21.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.21.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.21.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.21.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.21.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.22.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.22.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "f70cfed9fbc0410fa6b0797235cdab7d"
+ },
+ {
+ "dataPath": "params_shard_77.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.23.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "ede19a6adac155e641a20636a25c565c"
+ },
+ {
+ "dataPath": "params_shard_78.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.23.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "02c25ccb2ca599106bc5ecb1c8324a9c"
+ },
+ {
+ "dataPath": "params_shard_79.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.22.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.22.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.22.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.22.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.22.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.22.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.23.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.23.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "662bcf93de2404a25c60dbc309e38b31"
+ },
+ {
+ "dataPath": "params_shard_80.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.24.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "1ede2476ce7173f35a1cb49a6cba4e04"
+ },
+ {
+ "dataPath": "params_shard_81.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.24.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f7980da4d6e8ce62759af827d8c69b0c"
+ },
+ {
+ "dataPath": "params_shard_82.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.23.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.23.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.23.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.23.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.23.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.23.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.24.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.24.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "f304b900f29477eb0882c96e14899046"
+ },
+ {
+ "dataPath": "params_shard_83.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.25.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e843d7080faacd9c9e8f52fb87b0e7ef"
+ },
+ {
+ "dataPath": "params_shard_84.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.25.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "2a5b07fcbafbb5d0e0b785472a6d2efd"
+ },
+ {
+ "dataPath": "params_shard_85.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.24.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.24.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.24.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.24.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.24.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.24.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.25.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.25.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "d21b88653c36c0f66734079e4c60ab45"
+ },
+ {
+ "dataPath": "params_shard_86.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.26.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a197a4b56b9d1bb94b6927085b58ca98"
+ },
+ {
+ "dataPath": "params_shard_87.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.26.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "48dae4b9ea3f4551e74c9aa45c125735"
+ },
+ {
+ "dataPath": "params_shard_88.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.25.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.25.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.25.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.25.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.25.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.25.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.26.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.26.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "399899da1765cfacb382cfa5d8a9fc97"
+ },
+ {
+ "dataPath": "params_shard_89.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.27.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "531448467d8018eb56a925eaa570e943"
+ },
+ {
+ "dataPath": "params_shard_90.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.27.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "5e59bef0db8890aff878c5bd74751a4d"
+ },
+ {
+ "dataPath": "params_shard_91.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.26.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.26.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.26.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.26.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.26.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.26.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.27.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.27.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "0159ab1d84d4ea4d742f4a8f3bd94382"
+ },
+ {
+ "dataPath": "params_shard_92.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.28.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "3b682f5fadb8d5f1f1ecd87ff011670c"
+ },
+ {
+ "dataPath": "params_shard_93.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.28.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "7901da496411db5e4f0b174d1dea0a79"
+ },
+ {
+ "dataPath": "params_shard_94.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.27.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.27.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.27.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.27.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.27.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.27.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.28.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.28.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "fe16320cd078cebca0137a431c5b6f3d"
+ },
+ {
+ "dataPath": "params_shard_95.bin",
+ "format": "raw-shard",
+ "nbytes": 23527424,
+ "records": [
+ {
+ "name": "model.layers.29.mlp.down_proj.q_weight",
+ "shape": [
+ 4096,
+ 1436
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 23527424,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "8123f8a798bc7e2c71279865e3241b98"
+ },
+ {
+ "dataPath": "params_shard_96.bin",
+ "format": "raw-shard",
+ "nbytes": 47251456,
+ "records": [
+ {
+ "name": "model.layers.29.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 28672,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 47251456,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "8dc8529234a734394f5de3828d8eeac7"
+ },
+ {
+ "dataPath": "params_shard_97.bin",
+ "format": "raw-shard",
+ "nbytes": 27848704,
+ "records": [
+ {
+ "name": "model.layers.28.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.28.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.28.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.28.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.28.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.28.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ },
+ {
+ "name": "model.layers.29.input_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 24899584
+ },
+ {
+ "name": "model.layers.29.mlp.down_proj.q_scale",
+ "shape": [
+ 4096,
+ 359
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 2940928,
+ "byteOffset": 24907776
+ }
+ ],
+ "md5sum": "9f20bb2ed26d17cbd963a7d599f4eb03"
+ },
+ {
+ "dataPath": "params_shard_98.bin",
+ "format": "raw-shard",
+ "nbytes": 24899584,
+ "records": [
+ {
+ "name": "model.layers.29.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 28672,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 5906432,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.29.post_attention_layernorm.weight",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 8192,
+ "byteOffset": 5906432
+ },
+ {
+ "name": "model.layers.29.self_attn.qkv_proj.q_weight",
+ "shape": [
+ 6144,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 10125312,
+ "byteOffset": 5914624
+ },
+ {
+ "name": "model.layers.29.self_attn.qkv_proj.q_scale",
+ "shape": [
+ 6144,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 1265664,
+ "byteOffset": 16039936
+ },
+ {
+ "name": "model.layers.29.self_attn.o_proj.q_weight",
+ "shape": [
+ 4096,
+ 412
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 6750208,
+ "byteOffset": 17305600
+ },
+ {
+ "name": "model.layers.29.self_attn.o_proj.q_scale",
+ "shape": [
+ 4096,
+ 103
+ ],
+ "dtype": "float16",
+ "format": "f32-to-bf16",
+ "nbytes": 843776,
+ "byteOffset": 24055808
+ }
+ ],
+ "md5sum": "0943559980034c1ec5bdfd0f9b0e25f4"
+ }
+ ]
+}
\ No newline at end of file
diff --git a/params_shard_0.bin b/params_shard_0.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2fe5823de93166c2eb3707a37d21bddb381e18b9
--- /dev/null
+++ b/params_shard_0.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d655547c0c83abbd5d2e5c0c82b15aee436bed8a2f4f4b8bc5c3da5017a9446
+size 211365888
diff --git a/params_shard_1.bin b/params_shard_1.bin
new file mode 100644
index 0000000000000000000000000000000000000000..96e5f60cf8554d0650a29e4cb7c6be36442fdc3b
--- /dev/null
+++ b/params_shard_1.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d9e79af1cdc73ed89ecd1a5eee7d1536f90a3a7bbc752dd01e47f051e2b7668
+size 23527424
diff --git a/params_shard_10.bin b/params_shard_10.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c06e1b5307109f18de4ec195b22e7dc85120fe3c
--- /dev/null
+++ b/params_shard_10.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9ef8fb4da3726426b008736f685f601581da56c89b1d55e870f463767be240
+size 47251456
diff --git a/params_shard_11.bin b/params_shard_11.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9d9a9163c33706a565345a9dde0221ca552d1448
--- /dev/null
+++ b/params_shard_11.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0e42c1c2e0d9ddb25971dc296fbfd0dce96b209e855eeb744c687e790169eb
+size 27856896
diff --git a/params_shard_12.bin b/params_shard_12.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ae4a27693476db3d2e1dfa4976ae7ecf72dc4d2b
--- /dev/null
+++ b/params_shard_12.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa66de2a3212453f044eeef282f6c7ee085bac32a4e394eb784195813c8932b9
+size 23527424
diff --git a/params_shard_13.bin b/params_shard_13.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2becdd1bc9182fc0a64c42ad4b05f93195f9daea
--- /dev/null
+++ b/params_shard_13.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b59e32f81cfc4a7f3e2775ef072e190c2c421accd7e7fa16bd4a9506c754da
+size 47251456
diff --git a/params_shard_14.bin b/params_shard_14.bin
new file mode 100644
index 0000000000000000000000000000000000000000..941d3994a64680c9b28c3a198945d81758469fef
--- /dev/null
+++ b/params_shard_14.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5672e4ada0a66f52e48e741583d977e99690eab50c416466e7a607cf2f4c10a
+size 27848704
diff --git a/params_shard_15.bin b/params_shard_15.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1890c5104d2ffa93d98cccac6c93950e528f2bb2
--- /dev/null
+++ b/params_shard_15.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac00f51f963fc56dd5bb71091d38da0ec6f8770e2ab347678cf6bd7a13b521bd
+size 23527424
diff --git a/params_shard_16.bin b/params_shard_16.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c47b4240d3a8c2422620dc47cc30962f8bb487e
--- /dev/null
+++ b/params_shard_16.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af08b87e2f3ad36500e511a19a7c198aadab10fc5af03f75a5418d4d18cad597
+size 47251456
diff --git a/params_shard_17.bin b/params_shard_17.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e2564ce4e6a8f3a9b759157812892bfd84621ddf
--- /dev/null
+++ b/params_shard_17.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b24a850e05c1608b033c87b05d57951c0a1dad7caa1bfe76cfd0ce8f063878b
+size 27848704
diff --git a/params_shard_18.bin b/params_shard_18.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e0cd5f182b29d302ec8c682e18aeadc59a05c114
--- /dev/null
+++ b/params_shard_18.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8706246444fafcad7d4e3a735738d1f4cfd9231a20fa8759dca33eb8520b8ce9
+size 23527424
diff --git a/params_shard_19.bin b/params_shard_19.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1ed18e5a166171c7b27ec91389cab12b2e576efb
--- /dev/null
+++ b/params_shard_19.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a762923ed858b1035a4fc3e352aa6c96965588c9574993d90073cf04968e2aa
+size 47251456
diff --git a/params_shard_2.bin b/params_shard_2.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6ca691c8b29091c460faeb2d33199aa0e5c78be5
--- /dev/null
+++ b/params_shard_2.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fb4667c5208c4d14776efed45450c0631d9ea540b5e8c0821ccd407c289f7f9
+size 47251456
diff --git a/params_shard_20.bin b/params_shard_20.bin
new file mode 100644
index 0000000000000000000000000000000000000000..78ee55c33403f09ceff59c90ce5d44fb71ec29e5
--- /dev/null
+++ b/params_shard_20.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15a4206a31c41bea87296818045845c6e8c91871ad5430a5c6729a2c8e5d818
+size 27848704
diff --git a/params_shard_21.bin b/params_shard_21.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2fa251aded5d05619c1cfacbf476c1a844b30f58
--- /dev/null
+++ b/params_shard_21.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45bb0b6e15b6f2b172c5a5ca7a5357ef5a363d76bb5b80cba050d84798b31d37
+size 23527424
diff --git a/params_shard_22.bin b/params_shard_22.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9ff1b046a3be3e0a496127b872b48a096067256a
--- /dev/null
+++ b/params_shard_22.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:485d54b0d7b9567597c5a7fa6ebf5eef230258524d56b8314ed63288dc950fc8
+size 47251456
diff --git a/params_shard_23.bin b/params_shard_23.bin
new file mode 100644
index 0000000000000000000000000000000000000000..81de0aef45d022a2bd11eaf47e42113a56bf5b59
--- /dev/null
+++ b/params_shard_23.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d168a4a326eb2bd3cde4021ef4227076d00e6ea3a8dad5f76bd40cf06b3e0e76
+size 27848704
diff --git a/params_shard_24.bin b/params_shard_24.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b3a9e63a5ed1826073a7d1e350dbf2f3fe4e9d9a
--- /dev/null
+++ b/params_shard_24.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c816f02bf6d752707770cb9d2a10349e2ca69b21bab6724a942d3e2466b46c
+size 23527424
diff --git a/params_shard_25.bin b/params_shard_25.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3e27c861f00c3408db58589fe57445892e568150
--- /dev/null
+++ b/params_shard_25.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a3c9da2aaa45610166d9b0580350bb27b755bfe2cc5fb3289e6a849ea72426d
+size 47251456
diff --git a/params_shard_26.bin b/params_shard_26.bin
new file mode 100644
index 0000000000000000000000000000000000000000..44591378a00b4a13d544a6be41fcc66a25ccd61b
--- /dev/null
+++ b/params_shard_26.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa386652c031bf1941acc19165f907c6f75392863520f1fd9fc6b2cba292365
+size 27848704
diff --git a/params_shard_27.bin b/params_shard_27.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3760bdacd406b92def1dfe8aec1f7324c406c2a4
--- /dev/null
+++ b/params_shard_27.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb920e2bd4dfdfef526496d6d37b541fab710cc74121da423915fe03b4971e70
+size 23527424
diff --git a/params_shard_28.bin b/params_shard_28.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3309be8a6137a22825e9f3ddfe5533285f3bcd32
--- /dev/null
+++ b/params_shard_28.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b9b61e886e949a717a0610074a1b0ab174dddf2fcb07ffbd3892a90e2bfaf0
+size 47251456
diff --git a/params_shard_29.bin b/params_shard_29.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1894658985c618beaa966778ddb4883874f264a5
--- /dev/null
+++ b/params_shard_29.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52fea74c94383af354efe83fa521d2ebaf51ec49c690d84e5b2eaa25d2813b5f
+size 27848704
diff --git a/params_shard_3.bin b/params_shard_3.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c36998038377b1428e4c18e75253586b707051d8
--- /dev/null
+++ b/params_shard_3.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e6f7c6b47af15c6801045c2ce4b7400e881fc22c914a57ca6de1dbea672c569
+size 29369856
diff --git a/params_shard_30.bin b/params_shard_30.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c34ca4e4f042ad2a9e597f494697ea2d0f598e8f
--- /dev/null
+++ b/params_shard_30.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0471db5f18ff2bb30afea1f7a67e47954536c2ee48bb49ba410b9fe042286be
+size 23527424
diff --git a/params_shard_31.bin b/params_shard_31.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d3f03612cb81d22cf3f4c9186dc8ab5d1d9bcc61
--- /dev/null
+++ b/params_shard_31.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2abd4e0bd4ec7c6a8696d064f1249a47ebf2f2b2eb57f0546b13e8a72db2de7f
+size 47251456
diff --git a/params_shard_32.bin b/params_shard_32.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7d2215f1aa583c53b46617c28ecbd8f6a37de24a
--- /dev/null
+++ b/params_shard_32.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bede54a809c6b922a86c0928e2f4ebf035709b974c15f9ab1c1a6dd640b1e207
+size 27848704
diff --git a/params_shard_33.bin b/params_shard_33.bin
new file mode 100644
index 0000000000000000000000000000000000000000..344af95db03166821c054407e7f822e1ab3eb216
--- /dev/null
+++ b/params_shard_33.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b141d5740c6ef4e9531e00756ed9e2b189019cae397b32c06e105f3411eb5247
+size 47251456
diff --git a/params_shard_34.bin b/params_shard_34.bin
new file mode 100644
index 0000000000000000000000000000000000000000..acd2d4bb377e68ad7ab91cde0568e99d639d727e
--- /dev/null
+++ b/params_shard_34.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:125968111777a825d1a7a7492d8c43a91083a0f1030ea16aaa78fb8213a20dbb
+size 30806016
diff --git a/params_shard_35.bin b/params_shard_35.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4f672705ed90e03cb3eb2d6608d7862b3e2eb4a0
--- /dev/null
+++ b/params_shard_35.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a38fa6e1f449afd0fa38657cc9e64b6519f49a30c297ddc792379ac2a7e5014
+size 23527424
diff --git a/params_shard_36.bin b/params_shard_36.bin
new file mode 100644
index 0000000000000000000000000000000000000000..10c5c2fb9c8ecf2038d22976d38bb8b018763bb1
--- /dev/null
+++ b/params_shard_36.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb72ec3e1289efa1f00b6650967a1cd7eb9a84e6c13c761dfd6575b4f191e114
+size 47251456
diff --git a/params_shard_37.bin b/params_shard_37.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9220f66877fb49909ab45b8b593343656af8c44b
--- /dev/null
+++ b/params_shard_37.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fcfc632331131dfe4e29f2201d81c8f46a100c7aa0b499f2142118883bdd2f5
+size 27848704
diff --git a/params_shard_38.bin b/params_shard_38.bin
new file mode 100644
index 0000000000000000000000000000000000000000..df46fd92c5d287cfa049eb4fb4c55f48dd3d8124
--- /dev/null
+++ b/params_shard_38.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d55684f17d56311ef6150918e198d81849174edd2f4766f1caf4feaca89e06
+size 23527424
diff --git a/params_shard_39.bin b/params_shard_39.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6c6d723c4102ac958a30f57774fa11b0c381dc64
--- /dev/null
+++ b/params_shard_39.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a377ef3dedc97fdd75d3b7331d93aead5fb6424654bba85a0f35e574717d47f1
+size 47251456
diff --git a/params_shard_4.bin b/params_shard_4.bin
new file mode 100644
index 0000000000000000000000000000000000000000..479ad2c76b3fb2039b0eb7de969695007db67364
--- /dev/null
+++ b/params_shard_4.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0bdb289e813e5556fc71da917553e5114a8c198a35f9c9824dcc38b4d79994e
+size 23527424
diff --git a/params_shard_40.bin b/params_shard_40.bin
new file mode 100644
index 0000000000000000000000000000000000000000..669bfc7e28ee88bd3daaa2405c6cc0640a08a1b2
--- /dev/null
+++ b/params_shard_40.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b220850213283372cb572ccc2fa8b9cff79d4927d6db469e1cbeff0ea5cb00
+size 27848704
diff --git a/params_shard_41.bin b/params_shard_41.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3053501a6668e61c5f2e4b33bad591742d71311a
--- /dev/null
+++ b/params_shard_41.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:701d051da9ea8dc4c728cac557b2b514552757133cbee63f0daf817c041f49d8
+size 23527424
diff --git a/params_shard_42.bin b/params_shard_42.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5140e42c9b285fef6a553832394d24a84168c9c5
--- /dev/null
+++ b/params_shard_42.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8455c26fb52fe09548ab32f09bbbc40b4fcdc73a342eb3a25daf5d024bec3b
+size 47251456
diff --git a/params_shard_43.bin b/params_shard_43.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5ef2f309baaaecda5471fae2b728a5c64463df08
--- /dev/null
+++ b/params_shard_43.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc0b072aeb1d49e03be15fb6c0867389c0f4e2f28dd5e08bb070264259869b6
+size 27848704
diff --git a/params_shard_44.bin b/params_shard_44.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3e59004718349e6742d0afdbcc10c6b9db7975a3
--- /dev/null
+++ b/params_shard_44.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73b0f28c2d2ae550ce7a44d84d81b1aa3457f4285e4f3adf94a755ebe255b0f
+size 23527424
diff --git a/params_shard_45.bin b/params_shard_45.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2dfe263ccc4d258deb9e7536a870280ce33a1909
--- /dev/null
+++ b/params_shard_45.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c82226bd18e5e4c6d51f791d98b2be189594d61a0ad0cb73cfb5deb0ce4adaad
+size 47251456
diff --git a/params_shard_46.bin b/params_shard_46.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5afc5aed3161b20b90511a6cabf6da752fabcf1b
--- /dev/null
+++ b/params_shard_46.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b59c9468174d3dfaa851348fdf49aac6ce5ed6ae728d72c215f50c66001869b
+size 27848704
diff --git a/params_shard_47.bin b/params_shard_47.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4f0af612a3889b231196166256bd2253aa4aaaf1
--- /dev/null
+++ b/params_shard_47.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:756a8840cb74443e51348e309100df0ff40dff070688083337b2db3f618c8d7b
+size 23527424
diff --git a/params_shard_48.bin b/params_shard_48.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2e467a737d8c9cb0a584d56e285010525c4c4c71
--- /dev/null
+++ b/params_shard_48.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a10d850c95409bdd37e1ce52452c9f96d50beac9be70f6ecd75a2cb50ebd627
+size 47251456
diff --git a/params_shard_49.bin b/params_shard_49.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f6682c7dc7540e12b933f46b2fdd1f802b5ae601
--- /dev/null
+++ b/params_shard_49.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecfcc45d122c7d5c794ca34123b10b37d5461b821839081fdab4d4cb1aafceb4
+size 27848704
diff --git a/params_shard_5.bin b/params_shard_5.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2322dbddc40b243f947b4af900fc4cbce4c4a64b
--- /dev/null
+++ b/params_shard_5.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a402d6df657e4df1be9589f17cb70bb6a3f58efd372171690d461457975406
+size 47251456
diff --git a/params_shard_50.bin b/params_shard_50.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e9464835d6cb9972e8116045c76996efc4d85a1d
--- /dev/null
+++ b/params_shard_50.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0fb3ce09602d95403d7ca88127f54b0eb74c88635760759d26adba077df03f9
+size 23527424
diff --git a/params_shard_51.bin b/params_shard_51.bin
new file mode 100644
index 0000000000000000000000000000000000000000..578a2cd0ce12af358464a15727ceab7da8d8202e
--- /dev/null
+++ b/params_shard_51.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adda64c1a4676985da2e782d6957ed6b26b43dda8012af45a22e81a4d30a2ac4
+size 47251456
diff --git a/params_shard_52.bin b/params_shard_52.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cd788dca1862a6e8d49bcfe5a5938bbea81bccc6
--- /dev/null
+++ b/params_shard_52.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629e6b4a5cea3f0794fc223038d1150e5f0bcdd15374e4443aadb07019ef6918
+size 27848704
diff --git a/params_shard_53.bin b/params_shard_53.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c1675bca78cc0cd5039a35515281f1769bad4790
--- /dev/null
+++ b/params_shard_53.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad2c23b1293001f1d173698778a0211f1826c0b0aff48b661b02054393a42ce
+size 23527424
diff --git a/params_shard_54.bin b/params_shard_54.bin
new file mode 100644
index 0000000000000000000000000000000000000000..07b652b704e6f817f3ea228797d02ea7ad1ab11d
--- /dev/null
+++ b/params_shard_54.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd0254e673becb136aa5898990b14f50b2d143ed0062de4c9562942a0dddca8
+size 47251456
diff --git a/params_shard_55.bin b/params_shard_55.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e2ac0b88dec3e1a5425492934af7e9d44d763248
--- /dev/null
+++ b/params_shard_55.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e284204cf44b50230a915cba8450f39d4e53da6cdda0435c0274874320ca24f1
+size 27848704
diff --git a/params_shard_56.bin b/params_shard_56.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fa95f68b100f6a1155aaa805f790c62465628e67
--- /dev/null
+++ b/params_shard_56.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10281306a7e6c2b46d21250f0c7ab37da9b774f8e1490381e2942285d68466d2
+size 23527424
diff --git a/params_shard_57.bin b/params_shard_57.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8dd4708ee07835e8c1accffa91ebe7eeeca3b473
--- /dev/null
+++ b/params_shard_57.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5bd1761086fe12ff695f14e223b978053a27eda30e21b0ff9c0bf5363672c3
+size 47251456
diff --git a/params_shard_58.bin b/params_shard_58.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8b0bfe315aeb2ee3d45a41181b00e76dce97d6b1
--- /dev/null
+++ b/params_shard_58.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d5b8c3525789a60e1a6ac23710b64c9c80ee210a29b22dfa3daefa511236bfb
+size 27848704
diff --git a/params_shard_59.bin b/params_shard_59.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3ab7d9cc85cd255bd3fb2c9e4db7ebd52389c36f
--- /dev/null
+++ b/params_shard_59.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8686162912044b4bb6b8a144ddf867f9d2cb4cc09208c245fe79faa9f3d40d
+size 23527424
diff --git a/params_shard_6.bin b/params_shard_6.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2b3b02b0313e03ab8301a2d4e30dd36f11fcec05
--- /dev/null
+++ b/params_shard_6.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:913f1126a19a395db4dfc0264564fa21a0eaff121729f6c5b819071489bdf8c4
+size 27848704
diff --git a/params_shard_60.bin b/params_shard_60.bin
new file mode 100644
index 0000000000000000000000000000000000000000..035f2652a8110dd745687da0d2cc6e719a649ee1
--- /dev/null
+++ b/params_shard_60.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:577a74f99bd061687bcf6c193732843ba82f2485b574317cbbd447d6c7a99bef
+size 47251456
diff --git a/params_shard_61.bin b/params_shard_61.bin
new file mode 100644
index 0000000000000000000000000000000000000000..90e827d4d00baa7720abd84530d8eec6e10cfb47
--- /dev/null
+++ b/params_shard_61.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae49640b98f5d59b871bdc4c083d5b4ac31e4e1923f40d38caa9241506478ac0
+size 27848704
diff --git a/params_shard_62.bin b/params_shard_62.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fc90a1bf6848d8c1bd18d7855d9df23f74890941
--- /dev/null
+++ b/params_shard_62.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ddbbd5c0ca25d1d59a711fbb3bf5ddc925f02c8f0a404a961ae807c4e81156
+size 30375936
diff --git a/params_shard_63.bin b/params_shard_63.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c0cb0fcb825166b1a37fa3a25ad40c671c4fe120
--- /dev/null
+++ b/params_shard_63.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26953eac29fdedb6f139c6efa3fd23b214bf1323a3bd4b434c946ef8694dbcb5
+size 31129600
diff --git a/params_shard_64.bin b/params_shard_64.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d48b27ef578b26c2c760432a973310fee0f4a96c
--- /dev/null
+++ b/params_shard_64.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfa9ab99a47abc8c61b54a1cf733daa976b06c3d7d9bbf1d73b84101896db95
+size 47251456
diff --git a/params_shard_65.bin b/params_shard_65.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1e45369f1c6ee10724a9c056f507b2944435fa4f
--- /dev/null
+++ b/params_shard_65.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e2f330fa19d6478e6f9c409dfe6126011155a80ffc7d6f579d40f26984bf6f
+size 29425664
diff --git a/params_shard_66.bin b/params_shard_66.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d36eeeb46545bab645e27a30d31bcb9cead127b2
--- /dev/null
+++ b/params_shard_66.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc533edb6962badc62af2f29c3dce5d530937cd000956b9c497fa29bde4e160
+size 23527424
diff --git a/params_shard_67.bin b/params_shard_67.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6c1d615d5e231ba5342ea4fe7785807bfe818ca8
--- /dev/null
+++ b/params_shard_67.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699c4445e09f9041e87c939f0d6ddd344b2f1565c72af5f832d0c3da44ea39bc
+size 47251456
diff --git a/params_shard_68.bin b/params_shard_68.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6a3c281bd5025f897b7a1d5c7b06992f44aceaf2
--- /dev/null
+++ b/params_shard_68.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b659e2b8a15c6f99c8fd8ff55779d3beed6611391828a7c4fcdcf467d4808804
+size 27848704
diff --git a/params_shard_69.bin b/params_shard_69.bin
new file mode 100644
index 0000000000000000000000000000000000000000..14b1526955fa98613902017eb0e67327361331dc
--- /dev/null
+++ b/params_shard_69.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b6b480389daaa62c312f0e0903e5f807ba34edbce3a6d2938ec23d20b9b47f
+size 47251456
diff --git a/params_shard_7.bin b/params_shard_7.bin
new file mode 100644
index 0000000000000000000000000000000000000000..dedb760410dd13918d09623995c4ad4b0ec21139
--- /dev/null
+++ b/params_shard_7.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9389328e7f0105192597cbb288d06c26fc4dab21574a486f1ed28c97ed5e3051
+size 211365888
diff --git a/params_shard_70.bin b/params_shard_70.bin
new file mode 100644
index 0000000000000000000000000000000000000000..10dd3702cda0cf0166de594d596120f3f0c6f60a
--- /dev/null
+++ b/params_shard_70.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1bcc34c867416c6a135a45647c2e88233a2eff9b20488e42b6eea26ee9b46e0
+size 32391168
diff --git a/params_shard_71.bin b/params_shard_71.bin
new file mode 100644
index 0000000000000000000000000000000000000000..01acf7a44a6c89f4a71693ffff453226e7b1f5f7
--- /dev/null
+++ b/params_shard_71.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acee338c6bb7268d8e31748d494cb468282f7985b36c8c5b1828dcaf7a6a1722
+size 23527424
diff --git a/params_shard_72.bin b/params_shard_72.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0c0fc248236f126aeba4f5ac048b1493a73165be
--- /dev/null
+++ b/params_shard_72.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:094b89301c80699ee20994404dd42ab9ab6345e7b0fd09f780a0bdc7340b5c66
+size 47251456
diff --git a/params_shard_73.bin b/params_shard_73.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1b1c5d6993c5f847515a8928d8f4a56ec65b372c
--- /dev/null
+++ b/params_shard_73.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af91aac2977c75eeb28f2ff91e9fc53a2843d235a97eb12dbb6f038079b35ef6
+size 27848704
diff --git a/params_shard_74.bin b/params_shard_74.bin
new file mode 100644
index 0000000000000000000000000000000000000000..45c7891a0327db1368fa4d3f9170eb093c655c36
--- /dev/null
+++ b/params_shard_74.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d06c10552b1d9b1a594fe96893cfc2b75cb56c2752eea099fc28ca83d078beb
+size 23527424
diff --git a/params_shard_75.bin b/params_shard_75.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c68d5ddebc63ec40bc8eeeb8d956a7c859e2c6b8
--- /dev/null
+++ b/params_shard_75.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95d01b554c94b6c9605e005c2bf3580cdf9d4b55ab288e5669aacedb0bea231
+size 47251456
diff --git a/params_shard_76.bin b/params_shard_76.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a58bdd0f8d49f561a23a575d9f0c953a3ad4c882
--- /dev/null
+++ b/params_shard_76.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:580386973e7c52500ed68df9e41764001575d8ea0e6ff64d9d0d540890ea10ce
+size 27848704
diff --git a/params_shard_77.bin b/params_shard_77.bin
new file mode 100644
index 0000000000000000000000000000000000000000..43f8a0b646aa59aded543c34dea5f84ff2fbe152
--- /dev/null
+++ b/params_shard_77.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0934338b11b320f0c854a27a2e2a91003cbfb11581844540973c2c986a10d3eb
+size 23527424
diff --git a/params_shard_78.bin b/params_shard_78.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6ed0d0619909ca3d881beeaa37835a38d9d30193
--- /dev/null
+++ b/params_shard_78.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd08f0087c7aedabf1d043b8d021bb047a6f121cf59cf17d2b7bbe5d863e0ead
+size 47251456
diff --git a/params_shard_79.bin b/params_shard_79.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0ebeb0c67e1324b05655b13b66ef549a7bdc018d
--- /dev/null
+++ b/params_shard_79.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:987d3c4efb7961d5a55cf44ab1d600bc918c79ad7e94b21ce4c7e037d649a54f
+size 27848704
diff --git a/params_shard_8.bin b/params_shard_8.bin
new file mode 100644
index 0000000000000000000000000000000000000000..24d38b36b782af360a38937f8909e1218e57e1bc
--- /dev/null
+++ b/params_shard_8.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c661965db960abde4ae122d199dadf12248d0031d14d25d0c1404d89556fd097
+size 26420736
diff --git a/params_shard_80.bin b/params_shard_80.bin
new file mode 100644
index 0000000000000000000000000000000000000000..efef68be2ba9ee988954863950b903ff34cdc753
--- /dev/null
+++ b/params_shard_80.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f641ad2aa72cb3a80d3e004eb4b3020b67ce18520f156e016f2514cd3dab992
+size 23527424
diff --git a/params_shard_81.bin b/params_shard_81.bin
new file mode 100644
index 0000000000000000000000000000000000000000..40fac9d69154cce82242e5244e7745141358ce74
--- /dev/null
+++ b/params_shard_81.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d9e0b3286490382217205d4a8181d31857e1a1396608c6e74e790ae45ab2858
+size 47251456
diff --git a/params_shard_82.bin b/params_shard_82.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1552731b9c40702df9a47dcf0b3f260d6ed0c628
--- /dev/null
+++ b/params_shard_82.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53442812d10a934c1c5f014d1d2999ceecd38ed02c2066af161487264796048
+size 27848704
diff --git a/params_shard_83.bin b/params_shard_83.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4f12bffbe0b515b0846d29ad1ca1e3c629b469c6
--- /dev/null
+++ b/params_shard_83.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c5ceb03075ea56bf0db8fe93dadb1714861be3bf64280059fc4cc0d7c52e71
+size 23527424
diff --git a/params_shard_84.bin b/params_shard_84.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a9072ff042c44a23a8752c2376565521790d9d85
--- /dev/null
+++ b/params_shard_84.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f6bc0c65ce234b4056e77876580256878b59f829789b771903fa622f1f7894
+size 47251456
diff --git a/params_shard_85.bin b/params_shard_85.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c4f1c5b31f4b685c38c9d71aa2f709416cebedc5
--- /dev/null
+++ b/params_shard_85.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08edff598db5158e38db2f8a0d4b8f8966e05e5d90f5bdfb13efb70a7182c11d
+size 27848704
diff --git a/params_shard_86.bin b/params_shard_86.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8d0d2db860ce057751638a0b0045ad20a889d3d5
--- /dev/null
+++ b/params_shard_86.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b584556788294013cb779df93abfbdae69a946cc1b151edc6ef9edd2fb45dd
+size 23527424
diff --git a/params_shard_87.bin b/params_shard_87.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0bbf608526d7ce53234d8315762bfc87062aa1de
--- /dev/null
+++ b/params_shard_87.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4538a13666b5fb518f33f0e860dcc6ac6a0410de5d4cb9eea9497b91575503a6
+size 47251456
diff --git a/params_shard_88.bin b/params_shard_88.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8dfce84eab786038d279c0029868df0f51d78fc9
--- /dev/null
+++ b/params_shard_88.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dccf2e36bb05407cbdb62c706a4f92d90b9435f2b271f8822162008a871392ac
+size 27848704
diff --git a/params_shard_89.bin b/params_shard_89.bin
new file mode 100644
index 0000000000000000000000000000000000000000..583500f0c34b4c71a219a376e29d20e500047e4c
--- /dev/null
+++ b/params_shard_89.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d911cd18d8d353ed274c582dee5f75dc1189f439383e92778460f8976a3bb84
+size 23527424
diff --git a/params_shard_9.bin b/params_shard_9.bin
new file mode 100644
index 0000000000000000000000000000000000000000..05a4ec6119e7f18c344c80157f9bc41c6bb786be
--- /dev/null
+++ b/params_shard_9.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47adce4f4ae097f26643eb897a27e78058548c32a20d27310af07b0663db57c6
+size 23527424
diff --git a/params_shard_90.bin b/params_shard_90.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cb6cb06de4b178fb7146c1b00648b32b16431223
--- /dev/null
+++ b/params_shard_90.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:551503e50a0cf1c5aa02bfb0b9c78807450c709637b23a8cc3c07d9b250d33f0
+size 47251456
diff --git a/params_shard_91.bin b/params_shard_91.bin
new file mode 100644
index 0000000000000000000000000000000000000000..95ebb0093d9d137d3fad94f4362e76208e7a841c
--- /dev/null
+++ b/params_shard_91.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eb4266df519b7a420e3138741c344d4035350039809fa2019df5d99152be5bc
+size 27848704
diff --git a/params_shard_92.bin b/params_shard_92.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c4c68e2890694ab18c71651c3b9fce160143afdc
--- /dev/null
+++ b/params_shard_92.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01498e82062cd316c40eeee15f382c05154b700cbb8eb0d7094a31a6fdcba6b5
+size 23527424
diff --git a/params_shard_93.bin b/params_shard_93.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cd9541a136a0c32e544a3812eed37255de4e6f5f
--- /dev/null
+++ b/params_shard_93.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f976a88a58eecdee9597060ab1cc9c0a3493a8da66807dec3146efde53b608
+size 47251456
diff --git a/params_shard_94.bin b/params_shard_94.bin
new file mode 100644
index 0000000000000000000000000000000000000000..07e8eab7cb1e55f6ea2eeb133ede813bd800768c
--- /dev/null
+++ b/params_shard_94.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f34aa5c504d282ebcc9c759979d8d4ae2de2ffe9a267a81a1fe34d249220af8
+size 27848704
diff --git a/params_shard_95.bin b/params_shard_95.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a728ec9150ba43fd42676c1a431564b9cbae540f
--- /dev/null
+++ b/params_shard_95.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a86605486537439d662049bedaa4e1d92491e632dc6c6dd5b5599c4edb54399
+size 23527424
diff --git a/params_shard_96.bin b/params_shard_96.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5a8c2a0b06d762cf308e8b6d4d985738868ceb9f
--- /dev/null
+++ b/params_shard_96.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82cdfbd2d125c4339e4b880001444cc22f9dab239203d9cb87cf01c827c71e4
+size 47251456
diff --git a/params_shard_97.bin b/params_shard_97.bin
new file mode 100644
index 0000000000000000000000000000000000000000..05d24d2c8b515744b26626b095cc33fca2d4da26
--- /dev/null
+++ b/params_shard_97.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb905f7b20262775e41f6fff5bb3f9fb91504307618bc7dcd0451cf05b352d2
+size 27848704
diff --git a/params_shard_98.bin b/params_shard_98.bin
new file mode 100644
index 0000000000000000000000000000000000000000..dac45a264524c689215b9a5bfb54a94141d251b9
--- /dev/null
+++ b/params_shard_98.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e927196ae4a0bc22df4f85515bb2a4a491561f9e53c32ce4e7bad2deee6955be
+size 24899584
diff --git a/private-llm-config.json b/private-llm-config.json
new file mode 100644
index 0000000000000000000000000000000000000000..121f0cfc6d91b9e2c9fc63bec3342a91fbc83782
--- /dev/null
+++ b/private-llm-config.json
@@ -0,0 +1,51 @@
+{
+ "model_type": "llama",
+ "quantization": "w3a16g40sym",
+ "model_config": {
+ "hidden_size": 4096,
+ "intermediate_size": 14336,
+ "num_attention_heads": 32,
+ "num_hidden_layers": 32,
+ "rms_norm_eps": 1e-05,
+ "vocab_size": 128256,
+ "rope_theta": 500000.0,
+ "tie_word_embeddings": false,
+ "rope_scaling": {
+ "factor": 8.0,
+ "high_freq_factor": 4.0,
+ "low_freq_factor": 1.0,
+ "original_max_position_embeddings": 8192,
+ "rope_type": "llama3"
+ },
+ "context_window_size": 4096,
+ "prefill_chunk_size": 128,
+ "num_key_value_heads": 8,
+ "head_dim": 128,
+ "tensor_parallel_shards": 1,
+ "pipeline_parallel_stages": 1,
+ "max_batch_size": 80
+ },
+ "vocab_size": 128256,
+ "context_window_size": 4096,
+ "sliding_window_size": -1,
+ "prefill_chunk_size": 128,
+ "attention_sink_size": -1,
+ "tensor_parallel_shards": 1,
+ "mean_gen_len": 128,
+ "max_gen_len": 512,
+ "shift_fill_factor": 0.3,
+ "temperature": 0.6,
+ "presence_penalty": 0.0,
+ "frequency_penalty": 0.0,
+ "repetition_penalty": 1.0,
+ "top_p": 0.9,
+ "conv_template": "llama-3",
+ "pad_token_id": 0,
+ "bos_token_id": 128000,
+ "eos_token_id": 128040,
+ "tokenizer_files": [
+ "tokenizer.json",
+ "tokenizer_config.json"
+ ],
+ "version": "0.1.0"
+}
\ No newline at end of file
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
+size 17209403
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a26d9aac1c48d1725bde102f71e6032b3db9c236
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,2074 @@
+{
+ "added_tokens_decoder": {
+ "128000": {
+ "content": "<|begin_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128001": {
+ "content": "<|end_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128002": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128003": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128004": {
+ "content": "<|finetune_right_pad_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128005": {
+ "content": "<|reserved_special_token_2|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128006": {
+ "content": "<|start_header_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128007": {
+ "content": "<|end_header_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128008": {
+ "content": "<|eom_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128009": {
+ "content": "<|eot_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128010": {
+ "content": "<|python_tag|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128011": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128012": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128013": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128014": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128015": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128016": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128017": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128018": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128019": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128020": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128021": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128022": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128023": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128024": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128025": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128026": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128027": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128028": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128029": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128030": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128031": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128032": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128033": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128034": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128035": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128036": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128037": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128038": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128039": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128040": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128041": {
+ "content": "<|reserved_special_token_33|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128042": {
+ "content": "<|reserved_special_token_34|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128043": {
+ "content": "<|reserved_special_token_35|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128044": {
+ "content": "<|reserved_special_token_36|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128045": {
+ "content": "<|reserved_special_token_37|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128046": {
+ "content": "<|reserved_special_token_38|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128047": {
+ "content": "<|reserved_special_token_39|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128048": {
+ "content": "<|reserved_special_token_40|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128049": {
+ "content": "<|reserved_special_token_41|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128050": {
+ "content": "<|reserved_special_token_42|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128051": {
+ "content": "<|reserved_special_token_43|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128052": {
+ "content": "<|reserved_special_token_44|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128053": {
+ "content": "<|reserved_special_token_45|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128054": {
+ "content": "<|reserved_special_token_46|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128055": {
+ "content": "<|reserved_special_token_47|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128056": {
+ "content": "<|reserved_special_token_48|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128057": {
+ "content": "<|reserved_special_token_49|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128058": {
+ "content": "<|reserved_special_token_50|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128059": {
+ "content": "<|reserved_special_token_51|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128060": {
+ "content": "<|reserved_special_token_52|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128061": {
+ "content": "<|reserved_special_token_53|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128062": {
+ "content": "<|reserved_special_token_54|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128063": {
+ "content": "<|reserved_special_token_55|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128064": {
+ "content": "<|reserved_special_token_56|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128065": {
+ "content": "<|reserved_special_token_57|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128066": {
+ "content": "<|reserved_special_token_58|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128067": {
+ "content": "<|reserved_special_token_59|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128068": {
+ "content": "<|reserved_special_token_60|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128069": {
+ "content": "<|reserved_special_token_61|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128070": {
+ "content": "<|reserved_special_token_62|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128071": {
+ "content": "<|reserved_special_token_63|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128072": {
+ "content": "<|reserved_special_token_64|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128073": {
+ "content": "<|reserved_special_token_65|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128074": {
+ "content": "<|reserved_special_token_66|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128075": {
+ "content": "<|reserved_special_token_67|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128076": {
+ "content": "<|reserved_special_token_68|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128077": {
+ "content": "<|reserved_special_token_69|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128078": {
+ "content": "<|reserved_special_token_70|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128079": {
+ "content": "<|reserved_special_token_71|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128080": {
+ "content": "<|reserved_special_token_72|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128081": {
+ "content": "<|reserved_special_token_73|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128082": {
+ "content": "<|reserved_special_token_74|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128083": {
+ "content": "<|reserved_special_token_75|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128084": {
+ "content": "<|reserved_special_token_76|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128085": {
+ "content": "<|reserved_special_token_77|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128086": {
+ "content": "<|reserved_special_token_78|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128087": {
+ "content": "<|reserved_special_token_79|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128088": {
+ "content": "<|reserved_special_token_80|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128089": {
+ "content": "<|reserved_special_token_81|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128090": {
+ "content": "<|reserved_special_token_82|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128091": {
+ "content": "<|reserved_special_token_83|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128092": {
+ "content": "<|reserved_special_token_84|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128093": {
+ "content": "<|reserved_special_token_85|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128094": {
+ "content": "<|reserved_special_token_86|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128095": {
+ "content": "<|reserved_special_token_87|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128096": {
+ "content": "<|reserved_special_token_88|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128097": {
+ "content": "<|reserved_special_token_89|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128098": {
+ "content": "<|reserved_special_token_90|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128099": {
+ "content": "<|reserved_special_token_91|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128100": {
+ "content": "<|reserved_special_token_92|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128101": {
+ "content": "<|reserved_special_token_93|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128102": {
+ "content": "<|reserved_special_token_94|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128103": {
+ "content": "<|reserved_special_token_95|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128104": {
+ "content": "<|reserved_special_token_96|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128105": {
+ "content": "<|reserved_special_token_97|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128106": {
+ "content": "<|reserved_special_token_98|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128107": {
+ "content": "<|reserved_special_token_99|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128108": {
+ "content": "<|reserved_special_token_100|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128109": {
+ "content": "<|reserved_special_token_101|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128110": {
+ "content": "<|reserved_special_token_102|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128111": {
+ "content": "<|reserved_special_token_103|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128112": {
+ "content": "<|reserved_special_token_104|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128113": {
+ "content": "<|reserved_special_token_105|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128114": {
+ "content": "<|reserved_special_token_106|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128115": {
+ "content": "<|reserved_special_token_107|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128116": {
+ "content": "<|reserved_special_token_108|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128117": {
+ "content": "<|reserved_special_token_109|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128118": {
+ "content": "<|reserved_special_token_110|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128119": {
+ "content": "<|reserved_special_token_111|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128120": {
+ "content": "<|reserved_special_token_112|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128121": {
+ "content": "<|reserved_special_token_113|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128122": {
+ "content": "<|reserved_special_token_114|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128123": {
+ "content": "<|reserved_special_token_115|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128124": {
+ "content": "<|reserved_special_token_116|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128125": {
+ "content": "<|reserved_special_token_117|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128126": {
+ "content": "<|reserved_special_token_118|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128127": {
+ "content": "<|reserved_special_token_119|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128128": {
+ "content": "<|reserved_special_token_120|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128129": {
+ "content": "<|reserved_special_token_121|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128130": {
+ "content": "<|reserved_special_token_122|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128131": {
+ "content": "<|reserved_special_token_123|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128132": {
+ "content": "<|reserved_special_token_124|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128133": {
+ "content": "<|reserved_special_token_125|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128134": {
+ "content": "<|reserved_special_token_126|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128135": {
+ "content": "<|reserved_special_token_127|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128136": {
+ "content": "<|reserved_special_token_128|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128137": {
+ "content": "<|reserved_special_token_129|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128138": {
+ "content": "<|reserved_special_token_130|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128139": {
+ "content": "<|reserved_special_token_131|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128140": {
+ "content": "<|reserved_special_token_132|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128141": {
+ "content": "<|reserved_special_token_133|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128142": {
+ "content": "<|reserved_special_token_134|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128143": {
+ "content": "<|reserved_special_token_135|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128144": {
+ "content": "<|reserved_special_token_136|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128145": {
+ "content": "<|reserved_special_token_137|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128146": {
+ "content": "<|reserved_special_token_138|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128147": {
+ "content": "<|reserved_special_token_139|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128148": {
+ "content": "<|reserved_special_token_140|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128149": {
+ "content": "<|reserved_special_token_141|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128150": {
+ "content": "<|reserved_special_token_142|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128151": {
+ "content": "<|reserved_special_token_143|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128152": {
+ "content": "<|reserved_special_token_144|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128153": {
+ "content": "<|reserved_special_token_145|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128154": {
+ "content": "<|reserved_special_token_146|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128155": {
+ "content": "<|reserved_special_token_147|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128156": {
+ "content": "<|reserved_special_token_148|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128157": {
+ "content": "<|reserved_special_token_149|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128158": {
+ "content": "<|reserved_special_token_150|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128159": {
+ "content": "<|reserved_special_token_151|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128160": {
+ "content": "<|reserved_special_token_152|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128161": {
+ "content": "<|reserved_special_token_153|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128162": {
+ "content": "<|reserved_special_token_154|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128163": {
+ "content": "<|reserved_special_token_155|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128164": {
+ "content": "<|reserved_special_token_156|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128165": {
+ "content": "<|reserved_special_token_157|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128166": {
+ "content": "<|reserved_special_token_158|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128167": {
+ "content": "<|reserved_special_token_159|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128168": {
+ "content": "<|reserved_special_token_160|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128169": {
+ "content": "<|reserved_special_token_161|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128170": {
+ "content": "<|reserved_special_token_162|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128171": {
+ "content": "<|reserved_special_token_163|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128172": {
+ "content": "<|reserved_special_token_164|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128173": {
+ "content": "<|reserved_special_token_165|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128174": {
+ "content": "<|reserved_special_token_166|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128175": {
+ "content": "<|reserved_special_token_167|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128176": {
+ "content": "<|reserved_special_token_168|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128177": {
+ "content": "<|reserved_special_token_169|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128178": {
+ "content": "<|reserved_special_token_170|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128179": {
+ "content": "<|reserved_special_token_171|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128180": {
+ "content": "<|reserved_special_token_172|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128181": {
+ "content": "<|reserved_special_token_173|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128182": {
+ "content": "<|reserved_special_token_174|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128183": {
+ "content": "<|reserved_special_token_175|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128184": {
+ "content": "<|reserved_special_token_176|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128185": {
+ "content": "<|reserved_special_token_177|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128186": {
+ "content": "<|reserved_special_token_178|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128187": {
+ "content": "<|reserved_special_token_179|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128188": {
+ "content": "<|reserved_special_token_180|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128189": {
+ "content": "<|reserved_special_token_181|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128190": {
+ "content": "<|reserved_special_token_182|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128191": {
+ "content": "<|reserved_special_token_183|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128192": {
+ "content": "<|reserved_special_token_184|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128193": {
+ "content": "<|reserved_special_token_185|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128194": {
+ "content": "<|reserved_special_token_186|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128195": {
+ "content": "<|reserved_special_token_187|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128196": {
+ "content": "<|reserved_special_token_188|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128197": {
+ "content": "<|reserved_special_token_189|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128198": {
+ "content": "<|reserved_special_token_190|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128199": {
+ "content": "<|reserved_special_token_191|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128200": {
+ "content": "<|reserved_special_token_192|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128201": {
+ "content": "<|reserved_special_token_193|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128202": {
+ "content": "<|reserved_special_token_194|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128203": {
+ "content": "<|reserved_special_token_195|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128204": {
+ "content": "<|reserved_special_token_196|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128205": {
+ "content": "<|reserved_special_token_197|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128206": {
+ "content": "<|reserved_special_token_198|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128207": {
+ "content": "<|reserved_special_token_199|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128208": {
+ "content": "<|reserved_special_token_200|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128209": {
+ "content": "<|reserved_special_token_201|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128210": {
+ "content": "<|reserved_special_token_202|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128211": {
+ "content": "<|reserved_special_token_203|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128212": {
+ "content": "<|reserved_special_token_204|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128213": {
+ "content": "<|reserved_special_token_205|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128214": {
+ "content": "<|reserved_special_token_206|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128215": {
+ "content": "<|reserved_special_token_207|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128216": {
+ "content": "<|reserved_special_token_208|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128217": {
+ "content": "<|reserved_special_token_209|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128218": {
+ "content": "<|reserved_special_token_210|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128219": {
+ "content": "<|reserved_special_token_211|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128220": {
+ "content": "<|reserved_special_token_212|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128221": {
+ "content": "<|reserved_special_token_213|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128222": {
+ "content": "<|reserved_special_token_214|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128223": {
+ "content": "<|reserved_special_token_215|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128224": {
+ "content": "<|reserved_special_token_216|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128225": {
+ "content": "<|reserved_special_token_217|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128226": {
+ "content": "<|reserved_special_token_218|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128227": {
+ "content": "<|reserved_special_token_219|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128228": {
+ "content": "<|reserved_special_token_220|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128229": {
+ "content": "<|reserved_special_token_221|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128230": {
+ "content": "<|reserved_special_token_222|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128231": {
+ "content": "<|reserved_special_token_223|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128232": {
+ "content": "<|reserved_special_token_224|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128233": {
+ "content": "<|reserved_special_token_225|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128234": {
+ "content": "<|reserved_special_token_226|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128235": {
+ "content": "<|reserved_special_token_227|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128236": {
+ "content": "<|reserved_special_token_228|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128237": {
+ "content": "<|reserved_special_token_229|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128238": {
+ "content": "<|reserved_special_token_230|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128239": {
+ "content": "<|reserved_special_token_231|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128240": {
+ "content": "<|reserved_special_token_232|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128241": {
+ "content": "<|reserved_special_token_233|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128242": {
+ "content": "<|reserved_special_token_234|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128243": {
+ "content": "<|reserved_special_token_235|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128244": {
+ "content": "<|reserved_special_token_236|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128245": {
+ "content": "<|reserved_special_token_237|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128246": {
+ "content": "<|reserved_special_token_238|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128247": {
+ "content": "<|reserved_special_token_239|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128248": {
+ "content": "<|reserved_special_token_240|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128249": {
+ "content": "<|reserved_special_token_241|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128250": {
+ "content": "<|reserved_special_token_242|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128251": {
+ "content": "<|reserved_special_token_243|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128252": {
+ "content": "<|reserved_special_token_244|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128253": {
+ "content": "<|reserved_special_token_245|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128254": {
+ "content": "<|reserved_special_token_246|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128255": {
+ "content": "<|reserved_special_token_247|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|begin_of_text|>",
+ "chat_template": [
+ {
+ "name": "default",
+ "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+ },
+ {
+ "name": "tool_use",
+ "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": \"' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\n\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\n Returns:\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" \" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within XML tags as follows:\n\" }}\n{{- \"\n\" }}\n{{- '{\"name\": , \"arguments\": }\n' }}\n{{- '<|im_end|>\n' }}\n{%- for message in messages %}\n {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- for tool_call in message.tool_calls %}\n {{- '\n\n' }} {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '{' }}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"' }}\n {{- ', '}}\n {%- if tool_call.arguments is defined %}\n {{- '\"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments|tojson }}\n {%- endif %}\n {%- endif %}\n {{- '}' }}\n {{- '\n' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\n' }}\n {%- endif %}\n {{- '\n' }}\n {{- message.content }}\n {%- if not loop.last %}\n {{- '\n\n' }}\n {%- else %}\n {{- '\n' }}\n {%- endif %}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
+ }
+ ],
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|im_end|>",
+ "extra_special_tokens": {},
+ "legacy": false,
+ "model_input_names": [
+ "input_ids",
+ "attention_mask"
+ ],
+ "model_max_length": 131072,
+ "pad_token": "<|im_end|>",
+ "tokenizer_class": "PreTrainedTokenizerFast"
+}